MRpro - open PyTorch-based MR reconstruction and processing package

2025-07-30

AI Summary

Existing MR image reconstruction tools suffer from limited data operation consistency, inflexible algorithm design, poor deep learning integration, and low reproducibility. To address these limitations, we propose and open-source a modular, PyTorch-based framework for MR reconstruction and processing. The framework introduces a unified differentiable Fourier operator, an extensible phase map simulator, and a data-consistency layer supporting Cartesian, radial, spiral, and other sampling trajectories. It seamlessly integrates model-based optimization (e.g., proximal algorithms) with deep learning components—including learnable regularizers and composable network backbones—to enable motion correction, MR fingerprinting, and quantitative parameter mapping. Standardized data structures, public dataset interfaces, and plug-and-play operator design significantly improve reproducibility and collaborative development efficiency. We validate the framework’s generality and effectiveness across multiple quantitative imaging tasks.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We introduce MRpro, an open-source image reconstruction package built upon PyTorch and open data formats. The framework comprises three main areas. First, it provides unified data structures for the consistent manipulation of MR datasets and their associated metadata (e.g., k-space trajectories). Second, it offers a library of composable operators, proximable functionals, and optimization algorithms, including a unified Fourier operator for all common trajectories and an extended phase graph simulation for quantitative MR. These components are used to create ready-to-use implementations of key reconstruction algorithms. Third, for deep learning, MRpro includes essential building blocks such as data consistency layers, differentiable optimization layers, and state-of-the-art backbone networks and integrates public datasets to facilitate reproducibility. MRpro is developed as a collaborative project supported by automated quality control. We demonstrate the versatility of MRpro across multiple applications, including Cartesian, radial, and spiral acquisitions; motion-corrected reconstruction; cardiac MR fingerprinting; learned spatially adaptive regularization weights; model-based learned image reconstruction and quantitative parameter estimation. MRpro offers an extensible framework for MR image reconstruction. With reproducibility and maintainability at its core, it facilitates collaborative development and provides a foundation for future MR imaging research.

Problem

• Develops open-source PyTorch-based MR reconstruction framework
• Unifies data structures and operators for MR datasets
• Integrates deep learning blocks and public datasets for reproducibility

Innovation

• Unified data structures for MR datasets
• Composable operators and optimization algorithms
• Deep learning blocks with public datasets